{
  "source_file": "0930",
  "source_platform": "Dev.to",
  "author": "Bala Priya C",
  "title_listed": "Private AI: Machine Learning on Encrypted Data",
  "keywords": "",
  "domain": "机器学习",
  "content_type": "深度技术解析",
  "is_paid_flag": "否",
  "url": "https://dev.to/balapriya/private-ai-machine-learning-on-encrypted-data-3ldl",
  "publish_date": "2021-12-24",
  "corpus_stage": "",
  "notes": "",
  "id": "4f4099463b47",
  "collected_at": "2026-10-02T14:01:21",
  "title": "Private AI: Machine Learning on Encrypted Data - DEV Community",
  "body_markdown": "Kristin Lauter\nis currently the head of research science at Facebook AI Research (Meta), formerly the head of Cryptography and Privacy Research Group at Microsoft Research. This post is based on her talk at the OpenMined Privacy Conference.\nWhat is the privacy problem with AI?\nLet us begin by looking at a generic Machine Learning (ML) algorithm that takes in our data as input and outputs some kind of decision - a classification label, numerical value or a recommendation.\nThe privacy problem stems from the fact that we\nhave to input our data\nto get those nice and valuable predictions.\nMany AI applications powered by smart agents are hosted on the cloud, and protecting privacy of user data is pivotal to building secure applications.\nThe privacy of data can be protected through encryption. However, standard encryption methods do not allow computation on encrypted data. Here's where\nHomomorphic Encryption (HE)\nhelps.\nWhat is Homomorphic Encryption?\nIn simple terms, Homomorphic Encryption is a mathematical tool:\nthat allows for encryption of data,\nensuring privacy while at the same time, allowing computations to be performed on the encrypted data.\nThe result of computation can then be decrypted to get the results.\nAs shown in the figure below, with Homomorphic Encryption (HE), the order of encryption and computation can be interchanged.\nSuppose you have data\na\nand\nb\n. You can perform computation on the data and then encrypt the result, denoted by\nE(a*b)\n.\nAlternatively, you could encrypt the data and then perform computation, denoted by\nE(a) * E(b)\nin the figure below. If the encryption is homomorphic, then these two values,\nE(a*b)\nand\nE(a) * E(b)\ndecrypt to the same value.\nTherefore, we can choose to encrypt private data\na\nand\nb\n,\noutsource computation, say, to the cloud, and decrypt the obtained result of the computation to view the actual meaningful results.\nUnderstanding Homomorphic Encryption intuitively through Homer-morphic Encryption\nLet's try to think of a fictional character and draw a relatable analogy.\nRemember Homer Simpson from 'The Simpsons'?🙂\nThe following illustration is aimed at giving an intuitive explanation to what Homomorphic Encryption does.\nLet us say you need to get a jewel made and you have your gold ready! You'd now like to call your jeweler (Homer Simpson) and get your jewel made, however you're not very sure if your jeweler is trustworthy. Here's a suggestion.\nYou may place your gold in a box, lock it and keep the key with yourself. You may now invite over your jeweler and ask him to work on the gold nuggets through the glove box. Once the jewel is done, you may unlock your box and retrieve your jewel. Isn't that cool?\nLet us try to parse the analogy a bit.\nYour\nprivate data\nis analogous to gold,\noutsourcing computations\non encrypted data in a public environment is similar to getting your jeweler to work on the gold through glove box, and\ndecrypting\nthe results of computation to view the meaningful results is analogous to opening the box to get your jewel after the jeweler has left. 🙂\nWithout delving deep into the math involved, the high-level idea behind homomorphic encryption is as follows.\nHomomorphic Encryption uses\nlattice-based encoding\n.\nEncryption\nadds noise to a secret inner product.\nDecryption\nsubtracts the secret inner product and the noise becomes easy to cancel.\nIn the next section, let's see the capabilities of Microsoft SEAL, a library for Homomorphic Encryption.\nMicrosoft SEAL (Simple Encrypted Arithmetic Library)\nSEAL (Simple Encrypted Arithmetic Library) is Microsoft's library for Homomorphic Encryption (HE), widely adopted by research teams worldwide. It was first released publicly in 2015, followed by the standardization of HE in November 2018. Microsoft SEAL is available for download and use\nhere\n.\nIn recent years, availability of hardware accelerators has also enabled several orders of magnitude speedup. Here's a timeline of how Homomorphic Encryption has been adopted due to advances in research and easier access to compute.\nIdea: Computation on encrypted data without decrypting it\n2009: Considered impractical due to substantial overhead involved\n2011: Breakthrough at Microsoft Research\nSubsequent years of research: Practical encoding techniques that achieved several orders of speed-up\n2016: Crypto Nets at ICML 2016 - Neural Net predictions on encrypted data\nNow that we're familiar with how HE has been adopted over the years, the subsequent sections will focus on the possible applications of HE.\nCloud Compute Scenarios benefitting from HE\nThe following are some of the cloud computing scenarios that could potentially benefit from Homomorphic Encryption (HE):\nPrivate Storage and Computation\nPrivate Prediction Services\nHosted Private Training\nPrivate Set Intersection\nSecure Collaborative Computation\nThe markets benefitting from such services include healthcare, pharmaceutical, financial, government, insurance, manufacturing, oil and gas sector, to name a few. A few applications of Private AI across industries are listed below.\nFinance: Fraud detection, automated claims processing, threat intelligence, and data analytics are some applications.\nHealthcare: The scope of Private AI in healthcare includes medical diagnosis, medical support systems such as healthcare bots, preventive care and data analytics.\nManufacturing: Predictive maintenance and data analytics on potentially sensitive data.\nAzure ML Private Prediction\nAn image classification model for encrypted inferencing in Azure Container Instance (ACI), built on Microsoft SEAL, was announced at Microsoft Build Conference 2020. The tutorial can be accessed here.\nReferences\n[1]\nRecording of the PriCon talk",
  "metadata": {
    "title": "Private AI: Machine Learning on Encrypted Data - DEV Community",
    "description": "Kristin Lauter is currently the head of research science at Facebook AI Research (Meta), formerly the... Tagged with privacy, machinelearning, programming.",
    "keywords": "privacy, machinelearning, programming, software, coding, development, engineering, inclusive, community",
    "author": null,
    "og:type": "article",
    "og:url": "https://dev.to/balapriya/private-ai-machine-learning-on-encrypted-data-3ldl",
    "og:title": "Private AI: Machine Learning on Encrypted Data",
    "og:description": "Kristin Lauter is currently the head of research science at Facebook AI Research (Meta), formerly the...",
    "og:site_name": "DEV Community",
    "og:image": "https://media2.dev.to/dynamic/image/width=1000,height=500,fit=cover,gravity=auto,format=auto/https%3A%2F%2Fdev-to-uploads.s3.amazonaws.com%2Fuploads%2Farticles%2Fqncw4ezo71it8celzygi.jpg",
    "twitter:site": "@thepracticaldev",
    "twitter:creator": "@",
    "twitter:title": "Private AI: Machine Learning on Encrypted Data",
    "twitter:description": "Kristin Lauter is currently the head of research science at Facebook AI Research (Meta), formerly the...",
    "twitter:card": "summary_large_image",
    "twitter:widgets:new-embed-design": "on",
    "twitter:image:src": "https://media2.dev.to/dynamic/image/width=1000,height=500,fit=cover,gravity=auto,format=auto/https%3A%2F%2Fdev-to-uploads.s3.amazonaws.com%2Fuploads%2Farticles%2Fqncw4ezo71it8celzygi.jpg"
  },
  "paywall": {
    "listed_paid": false,
    "detected": false,
    "marker": "",
    "public_only": false,
    "policy": "付费/会员内容只保留页面公开可见部分，不绕过付费墙"
  },
  "crawl": {
    "success": true,
    "status_code": 200,
    "error": ""
  },
  "code_blocks": [],
  "images": [
    {
      "status": "ok",
      "url": "https://media2.dev.to/dynamic/image/width=800%2Cheight=%2Cfit=scale-down%2Cgravity=auto%2Cformat=auto/https%3A%2F%2Fblog.openmined.org%2Fcontent%2Fimages%2F2021%2F06%2F2m.png",
      "bytes": 7062,
      "reused": true,
      "local_path": "attachments/4f4099463b47/images/002.png",
      "src": "https://media2.dev.to/dynamic/image/width=800%2Cheight=%2Cfit=scale-down%2Cgravity=auto%2Cformat=auto/https%3A%2F%2Fblog.openmined.org%2Fcontent%2Fimages%2F2021%2F06%2F2m.png",
      "alt": "",
      "downloaded": true
    },
    {
      "status": "ok",
      "url": "https://media2.dev.to/dynamic/image/width=800%2Cheight=%2Cfit=scale-down%2Cgravity=auto%2Cformat=auto/https%3A%2F%2Fblog.openmined.org%2Fcontent%2Fimages%2F2021%2F06%2FScreenshot-2021-06-02-174615.jpg",
      "bytes": 7062,
      "reused": true,
      "local_path": "attachments/4f4099463b47/images/003.jpg",
      "src": "https://media2.dev.to/dynamic/image/width=800%2Cheight=%2Cfit=scale-down%2Cgravity=auto%2Cformat=auto/https%3A%2F%2Fblog.openmined.org%2Fcontent%2Fimages%2F2021%2F06%2FScreenshot-2021-06-02-174615.jpg",
      "alt": "",
      "downloaded": true
    }
  ],
  "audio": [],
  "videos": [
    {
      "url": "https://www.youtube.com/watch?v=78Ye1a24hyQ",
      "src": "https://www.youtube.com/watch?v=78Ye1a24hyQ",
      "status": "ok",
      "kind": "single_video",
      "local_path": "attachments/4f4099463b47/videos/repair-78Ye1a24hyQ.mp4",
      "bytes": 36777047,
      "valid": true,
      "height": 1080,
      "width": 1920,
      "duration": "762.521000",
      "reused": false
    }
  ],
  "links": [
    {
      "href": "https://scholar.google.com/citations?user=TmuUs30AAAAJ&hl=en",
      "label": "Kristin Lauter",
      "type": "a"
    },
    {
      "href": "https://media2.dev.to/dynamic/image/width=800%2Cheight=%2Cfit=scale-down%2Cgravity=auto%2Cformat=auto/https%3A%2F%2Fblog.openmined.org%2Fcontent%2Fimages%2F2021%2F06%2F2m.png",
      "label": "",
      "type": "a"
    },
    {
      "href": "https://media2.dev.to/dynamic/image/width=800%2Cheight=%2Cfit=scale-down%2Cgravity=auto%2Cformat=auto/https%3A%2F%2Fblog.openmined.org%2Fcontent%2Fimages%2F2021%2F06%2FScreenshot-2021-06-02-174615.jpg",
      "label": "",
      "type": "a"
    },
    {
      "href": "https://www.microsoft.com/en-us/research/project/microsoft-seal/",
      "label": "here",
      "type": "a"
    },
    {
      "href": "https://www.youtube.com/watch?v=78Ye1a24hyQ",
      "label": "Recording of the PriCon talk",
      "type": "a"
    }
  ],
  "repair_version": 2,
  "repaired_at": "2026-10-14T10:49:08Z",
  "source_url": "https://dev.to/balapriya/private-ai-machine-learning-on-encrypted-data-3ldl",
  "papers": [],
  "actual_video_files": [],
  "body_chars": 5705,
  "expected_body_images": 2,
  "discovery_status": "ok",
  "delivery_status": "ok",
  "missing_reason": "",
  "raw_html": "attachments/4f4099463b47/pages/source.html",
  "local_html": "attachments/4f4099463b47/pages/article.html",
  "body_base_path": "attachments/4f4099463b47/pages/",
  "body_markdown_path": "attachments/4f4099463b47/pages/article.md"
}